A text abstract generation method based on a K-means model and a neural network model

Abstract

The invention discloses a text abstract generation method based on a K-means model and a neural network model, and the method comprises the steps of preprocessing an original text, obtaining single sentences and words through segmentation, inputting the sentences and words into a doc2vec model, and carrying out the training, so as to obtain sentence vectors; determining the number of clustering centers of the original text, inputting the sentence vector into an unsupervised K-means model, and training to obtain a clustering center vector; calculating the Euclidean distance between the clustering center vector and the sentence vector, and extracting a sentence corresponding to the sentence vector closest to the clustering center to serve as a reference abstract; and inputting the original text, the reference abstract and the words into a generative neural network model to generate a text abstract. The method has the beneficial effects that the unsupervised model and the supervised neural network model are combined, so that the generated text abstract can be semantically coherent and is convenient for a user to understand.

Description

technical field [0001] The invention relates to the technical field of language processing, specifically, a method for generating text summaries based on a K-means model and a neural network model. Background technique [0002] We are in the era of information explosion. While enjoying the convenience brought by a variety of information, people are still eager to remove redundancy, refine and condense the core content of the obtained information, and use fewer sentences Replace the central idea of ​​information, thereby improving efficiency and saving search and reading time. A small number of scientific and technological articles contain abstracts, while news reports and social science articles do not contain abstracts, which requires readers to read the entire article to obtain the main information. The writing of these abstracts requires reading the entire article and an in-depth understanding of the article, so the process of writing an abstract requires a lot of manpow...

AI Technical Summary

Problems solved by technology

The writing of these abstracts requires reading the entire article and an in-depth understanding of the article, so the process of writing an abstract requires a lot of manpower and material resources. For some professional articles, editors with professional knowledge and industry experience are required, and those who can meet these requirements people are few

In today's society, the rapid development of the Internet and the sharp increase in the amount of information have led to an increasingly scarce manpower for manually compiling summaries. In order to obtain more important information, it is obviously unrealistic to invest a lot of manpower

[0003] The methods for automatically generating text summaries in the current technology are basically extractive, and the basic process is divided into two steps. First, the paragraphs, sentences, phrases, and keywords in the article are extracted through linguistic knowledge or statistical analysis; then the extracted The text is recombined to obtain a text summary. Although the extraction method is used to extract the summary to a certain extent, it can help people quickly understand the important information of the article, but the quality of the content and language is not satisfactory, because of Sentences are just a simple patchwork of important sentences in the original text, without logical correlative words, resulting in fragmented and ambiguous information, which can easily lead to inaccurate understanding by users

Images